GBrain: an open-source memory layer for AI agents
GBrain is an MIT-licensed, self-hostable memory layer for AI agents that, according to its project documentation, stores explicit facts with sources, supports corrections and withdrawals, and makes memory available across agents. It offers keyless memory and keyword retrieval, with optional semantic search, synthesis and background enrichment. An optional paid hosted service connects ChatGPT, Claude and Cursor. Project owner Garry Tan also says GBrain runs his OpenClaw and Hermes deployments, but the supplied report does not independently validate these features or production-use claims.
GBrain offers agent builders a portable memory system with source tracking, correction and withdrawal capabilities, local deployment and MCP access. Its effectiveness and production use remain attributed to the project owner.
Garry's Opinionated OpenClaw/Hermes Agent Brain
Give the agent you already use a memory you control. GBrain stores explicit facts with their sources, supports corrections and withdrawal, and makes the same memory available across your agents. Start with keyless memory and keyword retrieval; add semantic search, synthesis, and background enrichment when you need them.
GBrain is MIT-licensed and free to self-host; gbrain.io is optional paid hosting.
Tip
Need hosted? First time running an agent? Try gbrain.io, hosted GBrain, for the easiest experience: one brain for you and your team, connected to ChatGPT, Claude and Cursor, with nothing to install or keep online. Stuck? Email [email protected] and a person will set it up with you, free.